Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1277 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1158781 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0000

Data Index: 731822 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1080075 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1588. Min Act: -0.0000

Data Index: 1145419 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1113139 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1607. Min Act: -0.0000

Data Index: 397423 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1578. Min Act: -0.0000

Data Index: 871935 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1649354 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1150779 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1281303 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1494. Min Act: -0.0000

Data Index: 720512 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1053876 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1340335 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1489. Min Act: -0.0000

Data Index: 759022 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1533. Min Act: -0.0000

Data Index: 698070 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1495. Min Act: -0.0000

Data Index: 189679 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1255. Min Act: -0.0000

Data Index: 471828 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1442. Min Act: -0.0000

Data Index: 806518 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1454515 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1193207 (C4 (Web Text))

Max Activating Token Index: 463